A display apparatus includes: a display panel; a backlight unit including a plurality of backlight blocks; and a processor obtaining a current duty of a driving current for driving each of the plurality of backlight blocks by applying an artificial intelligence (AI) model to pixel information of an input image and driving the backlight unit based on the obtained current duty, in which the AI model is a model trained based on first luminance information included in an output image corresponding to each of a plurality of sample images and second luminance information corresponding to pixel information included in each of the plurality of sample images.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A display apparatus comprising: a display panel; a backlight unit including a plurality of backlight blocks; and a processor configured to: obtain a current duty of a driving current for driving each of the plurality of backlight blocks by applying an artificial intelligence (AI) model to pixel information of an input image, and drive the backlight unit based on the obtained current duty, wherein the AI model is trained based on first luminance information included in an output image corresponding to each of a plurality of sample images and second luminance information corresponding to pixel information included in each of the plurality of sample images.
2. The display apparatus as claimed in claim 1 , wherein the output image corresponding to each of the plurality of sample images is obtained by applying backlight local dimming to each of the plurality of sample images.
3. The display apparatus as claimed in claim 1 , wherein the AI model is trained based on the first luminance information included in the output image obtained by applying an initial AI model to each of the plurality of sample images and the second luminance information corresponding to the pixel information included in each of the plurality of sample images.
4. The display apparatus as claimed in claim 1 , wherein the processor is further configured to update the AI model based on third luminance information included in an output image output as the backlight unit is driven and fourth luminance information corresponding to pixel information included in the input image.
5. The display apparatus as claimed in claim 4 , wherein the processor is further configured to update the AI model based on a difference value between the third luminance information and the fourth luminance information, and based on receiving a new input image, the processor is further configured to obtain the current duty of the driving current for driving each of the plurality of backlight blocks by applying the updated AI model to pixel information of the received new input image.
6. The display apparatus as claimed in claim 4 , wherein the processor is further configured to predict at least one of light diffuser information or light transmission information based on a light profile of each light source included in each of the plurality of backlight blocks to obtain the third luminance information based on the predicted information.
7. The display apparatus as claimed in claim 1 , wherein the second luminance information is obtained by applying a reference current value to the pixel information included in each of the plurality of sample images.
8. The display apparatus as claimed in claim 1 , wherein the plurality of sample images comprises at least one of a full image or a block unit image.
9. The display apparatus as claimed in claim 1 , wherein the display panel comprises a liquid crystal panel.
10. The display apparatus as claimed in claim 1 , wherein the AI model comprises either a deep neural network (DNN) model configured to obtain a representative output value of each of the plurality of backlight blocks using dimensionality reduction on the input image or a combination of a plurality of DNN models.
11. A driving method of a display apparatus including a backlight unit, the driving method comprising: obtaining a current duty of a driving current for driving each of a plurality of backlight blocks included in the backlight unit by applying an artificial intelligence (AI) model to pixel information of an input image; and driving the backlight unit based on the obtained current duty, wherein the AI model is trained based on first luminance information included in an output image corresponding to each of a plurality of sample images and second luminance information corresponding to pixel information included in each of the plurality of sample images.
12. The driving method as claimed in claim 11 , wherein the output image corresponding to each of the plurality of sample images is obtained by applying backlight local dimming to each of the plurality of sample images.
13. The driving method as claimed in claim 11 , wherein the AI model is trained based on the first luminance information included in the output image obtained by applying an initial AI model to each of the plurality of sample images and the second luminance information corresponding to the pixel information included in each of the plurality of sample images.
14. The driving method as claimed in claim 11 , further comprising: updating the AI model based on third luminance information included in an output image output as the backlight unit is driven and fourth luminance information corresponding to pixel information included in the input image.
15. The driving method as claimed in claim 14 , wherein the updating the AI model further comprises updating the AI model based on a difference value between the third luminance information and the fourth luminance information, and the obtaining the current duty further comprises, based on receiving a new input image, obtaining the current duty of the driving current for driving each of the plurality of backlight blocks by applying the updated AI model to pixel information of the received new input image.
16. The driving method as claimed in claim 14 , further comprising: predicting at least one of light diffuser information or light transmission information based on a light profile of each light source included in each of the plurality of backlight blocks to obtain the third luminance information based on the predicted information.
17. The driving method as claimed in claim 11 , wherein the second luminance information is obtained by applying a reference current value to the pixel information included in each of the plurality of sample images.
18. The driving method as claimed in claim 11 , wherein the plurality of sample images comprises at least one of a full image or a block unit image.
19. The driving method as claimed in claim 11 , wherein a display panel included in the display apparatus comprises a liquid crystal panel.
20. The driving method as claimed in claim 11 , wherein the AI model comprises either a deep neural network (DNN) model obtaining a representative output value of each of the plurality of backlight blocks using dimensionality reduction on the input image or a combination of a plurality of DNN models.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
December 4, 2019
March 16, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.